QOCA® image Smart CXR Image Processing System is a software as medical device (SaMD) used, through artificial intelligence/deep learning technology, to analyze chest X-ray images of adult patient, and then identify cases with suspected pneumothorax. This product shall be used in conjunction with Picture Archiving and Communication System (PACS) at the hospital. This product will automatically analyze the DICOM files automatically pushed from PACS, and then make a notation next to the cases with suspected pneumothorax. This product is only used to remind radiologists to prioritize reviewing cases with suspected pneumothorax. Its results cannot be used as a substitute for a diagnosis by a radiologist, nor can it be used on a stand-alone basis for clinical decision-making.

Device Description

This product, QOCA® image Smart CXR Image Processing System, is a web-based medical device using a locked artificial intelligence algorithm. It provides features such as cases sorting and image viewing, and supports multiple users at a time.

After connecting to Picture Archiving and Communication System (PACS) at the hospital, this product is capable of automatically analyzing either posteroanterior (PA) view or anteroposterior (AP) erect view chest X-ray images automatically pushed from PACS. Once a case with suspected pneumothorax is identified, a notation will be made next to the case in question, so the radiologist can prioritize to review cases with suspected pneumothorax in the Viewer Page. This product will not directly indicate, however, the specific portions or anomalies on the image.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study details for the QOCA® image Smart CXR Image Processing System:

1. Acceptance Criteria and Reported Device Performance

Metric	Acceptance Criteria (Predicate Device K190362 Performance)	Reported Device Performance (QOCA® image Smart CXR)	Overall Performance
AUC	98.3% (95% CI: [97.40%, 99.02%])	97.8% (95% CI: [97.0%, 98.5%])	Met
Sensitivity	93.15% (95% CI: [87.76%, 96.67%])	92.5% (95% CI: [90.5%, 94.2%])	Met
Specificity	92.99% (95% CI: [90.19%, 95.19%])	94.0% (95% CI: [93.9%, 94.6%])	Met
Average Performance Time	22.1 seconds	4.94 seconds	Met

Note: The reported device performance is an overall performance across both the MIMIC and Taiwanese datasets. Individual performance for each dataset is also provided in the document.

2. Sample Size Used for the Test Set and Data Provenance

The device's performance was assessed using two separate pivotal studies/datasets:

MIMIC Dataset:
- Sample Size: 3,105 radiographs (336 positive pneumothorax cases, 2,769 negative pneumothorax cases).
- Data Provenance: US patient population (MIMIC dataset). This was an independent medical institution from the training dataset.
Taiwanese Dataset:
- Sample Size: 2,947 radiographs (472 positive pneumothorax cases, 2,475 negative pneumothorax cases).
- Data Provenance: Taiwanese hospital. This was an independent medical institution from the training dataset.

Overall Test Set: 6,052 radiographs (3,105 from MIMIC + 2,947 from Taiwan). Both datasets were retrospective.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

For both the MIMIC dataset and the Taiwanese dataset:

Number of Experts: Three radiologists.
Qualifications: The document states "truthed by three radiologists" without specifying their years of experience or sub-specialty.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method (e.g., 2+1, 3+1). It only mentions that the datasets were "truthed by three radiologists," implying a consensus-based approach, but the specific process for resolving disagreements is not detailed.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being performed to assess how much human readers improve with AI vs. without AI assistance. The study focused on the standalone performance of the AI algorithm.

6. Standalone Performance Study

Yes, a standalone performance study was done. The document explicitly states: "Bases on the results of the standalone performance assessment, this product achieves, identification accuracy of AUC > 95% with Sensitivity > 91% and Specificity > 92%." The performance metrics provided in section 1 (AUC, sensitivity, specificity) reflect the algorithm's performance without human-in-the-loop.

7. Type of Ground Truth Used

The ground truth for the test sets (MIMIC and Taiwanese) was established by "three radiologists," which indicates expert consensus diagnosis.

8. Sample Size for the Training Set

The document states: "The training dataset is used to train the model, and divided into three sets: the training set, the validation set, and the test set." However, the specific sample size for the entire training dataset (including training, validation, and its own internal test set used during development) is not provided in the summary. It only indicates that it was "collected from two hospitals, and additional data from the US National Institutes of Health (NIH) was added to the test set to improve its US patient population representativeness during training."

9. How the Ground Truth for the Training Set Was Established

The document states that the "model training dataset was collected from two hospitals, and additional data from the US National Institutes of Health (NIH) was added to the test set." While it implies the data was labeled for training, it does not explicitly describe how the ground truth for the training set was established (e.g., whether it was also by expert radiologists, pathology, etc.).

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" followed by the words "U.S. Food & Drug Administration".

Quanta Computer Inc. % Joe Wang Research Specialist No. 188, Wenhua 2nd Rd., Guishan Dist. Taoyuan City, 33383 TAIWAN

January 27, 2023

Re: K221868

Trade/Device Name: QOCA® image Smart CXR Image Processing System Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QFM Dated: December 9, 2022 Received: December 19, 2022

Dear Joe Wang:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

{1}------------------------------------------------

devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Jessica Lamb

Jessica Lamb, Ph.D. Assistant Director Imaging Software DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Traditional 510(k), K221868.AI2, Supplement 4 Section 4 - Indications for Use Statement (Form FDA 3881)

Supplement 4

Section 4 - Indications for Use Statement

(Form FDA 3881)

{3}------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration

Indications for Use

510(k) Number (if known) K221868

Device Name

QOCA® image Smart CXR Image Processing System

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)
☑ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the
time to review instructions, search existing data sources, gather and maintain the data needed and complete
and review the collection of information. Send comments regarding this burden estimate or any other aspect
of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{4}------------------------------------------------

Traditional 510(k), K221868.AI2, Supplement 5 Section 5 - 510(k) Summary

Supplement 5

Section 5 - 510(k) Summary

{5}------------------------------------------------

Traditional 510(k), K221868.AI2, Supplement 5 Section 5 - 510(k) Summary

510(k) SUMMARY

5.1 Type of Submission:	Traditional
5.2 Date of Summary:	01/19/2023
5.3 Submitter:	Quanta Computer Inc.
Address:	No. 188, Wenhua 2nd Rd., Guishan Dist., Taoyuan City 33383, Taiwan (R.O.C)
Phone:	+886-3-327-2345
Contact:	Joe Wang joe_wang@quantatw.com

5.4 Identification of the Device: Proprietary/Trade Name:

Proprietary/Trade Name:	QOCA® image Smart CXR ImageProcessing System
Model Number:	ZSWC001
Regulation Description:	Radiological Computer-AssistedPrioritization Software For Lesions
Review Panel:	Radiology
Regulation Number:	892.2080
Product Code:	QFM
Device Class:	II

ર.ડ Identification of the Predicate Device:

Predicate Device Name:	HealthPNX
Model Number:	—
510(k) Number:	K190362
Manufacturer:	Zebra Medical Vision Ltd.
Regulation Number:	892.2080
Product Code:	QFM
Device Class:	II

{6}------------------------------------------------

5.6 Intended Use/Indications for Use of the Device

5.7 Device Description

Bases on the results of the standalone performance assessment, this product achieves, identification accuracy of AUC > 95% with Sensitivity > 91% and Specificity > 92%.

The dataset used for training the algorithm was independent of the testing dataset. The training dataset included various characteristics, such as age, gender, radiographic positioning, radiography device, etc.

{7}------------------------------------------------

5.8 Comparison of Technological Characteristics with the Predicate Device

QOCA® image Smart CXR Image Processing System submitted in this 510(k) file is substantially equivalent in intended use, safety and performance to the cleared HealthPNX (K190362). Differences between the devices cited in this section do not raise any new issue of substantial equivalence.

Item	Subject device	Predicate device	Substantialequivalencedetermination
510(k) No.	K221868	K190362	-
Proprietary Name	QOCA® image Smart CXRImage Processing System	HealthPNX	-
Manufacturer	Quanta Computer Inc.	Zebra Medical Vision Ltd.	-
RegulationNumber	21 CFR 892.2080	21 CFR 892.2080	Same
Product Code	QFM	QFM	Same
Classification	Class II	Class II	Same
Intended Use	QOCA® image Smart CXRImage Processing System is asoftware as medical device(SaMD) used, through artificialintelligence/deep learningtechnology, to analyze chestX-ray images of adult patient,and then identify cases withsuspected pneumothorax. Thisproduct shall be used inconjunction with PictureArchiving and CommunicationSystem (PACS) at the hospital.This product will automaticallyanalyze the DICOM files	The Zebra Pneumothorax deviceis a software workflow tooldesigned to aid the clinicalassessment of adult Chest X-Raycases with features suggestive ofPneumothorax in the medicalcare environment.HealthPNX analyzes cases usingan artificial intelligencealgorithm to identify suspectedfindings.It makes case-level outputavailable to a PACS/workstationfor worklist prioritization ortriage. HealthPNX is not	SimilarBoth devices areintended to aid inworklist triage byproviding notificationof suspectedpneumothorax casesusing an artificialintelligence algorithm.They are not intendedto be used on astand-alone basis forclinicaldecision-making orclinical diagnosis.
Item	Subject device	Predicate device	Substantialequivalencedetermination
Notification-only,parallel workflowtool	automatically pushed fromPACS, and then make a notationnext to the cases with suspectedpneumothorax. This product isonly used to remind radiologiststo prioritize reviewing cases withsuspected pneumothorax. Itsresults cannot be used as asubstitute for a diagnosis by aradiologist, nor can it be used ona stand-alone basis for clinicaldecision-making.	intended to direct attention tospecific portions or anomalies ofan image. Its results are notintended to be used on astand-alone basis for clinicaldecision-making nor is itintended to rule outPneumothorax or otherwisepreclude clinical assessment ofX-Ray cases	Same
User	Radiologist	Radiologist	Same
Radiological imageformat	DICOM	DICOM	Same
Identify patientswith prespecifiedclinical condition	Yes	Yes	Same
Clinical condition	Pneumothorax	Pneumothorax	Same
Alert to finding	Passive notification flaggedfor review	Passive notification flaggedfor review	Same
Independent ofstandard of careworkflow	Yes; No cases are removedfrom worklist	Yes; No cases are removedfrom worklist	Same
Modality	X-Ray	X-Ray	Same
Body part	Chest	Chest	Same
Item	Subject device	Predicate device	Substantialequivalencedetermination
ArtificialIntelligencealgorithm	Yes	Yes	Same
Limited to analysisof imaging data	Yes	Yes	Same
Aids promptidentification ofcases with indicatedfindings	Yes	Yes	Same
Where results arereceived	Workstation	PACS/Workstation	SimilarThe subject device willbe connected withPACS and receivespatients' chest X-rayimages. The results willonly be presented onthe workstation.It will not raise anynew issues of safety orefficacy.
Time-to-notification	The average performance timeis 4.94 seconds.	The average performance timeis 22.1 seconds.	SameBoth devices canprovide effectivetriage.

{8}------------------------------------------------

Traditional 510(k), K221868.AI2, Supplement 5 Section 5 - 510(k) Summary

{9}------------------------------------------------

Traditional 510(k), K221868.AI2, Supplement 5 Section 5 - 510(k) Summary

{10}------------------------------------------------

Similarity and Difference

The subject device has the similar intended use to the predicate device. Both devices are intended to aid in worklist triage by providing notification of suspected pneumothorax cases using an artificial intelligence algorithm. And they are not intended to be used on a stand-alone basis for clinical decision-making or clinical diagnosis.

The slight difference between the subject device and the predicate is the result presentation. However, the result presenting of the subject device is within the scope of the predicate. Therefore, it will not affect the substantial equivalence.

5.9 Performance Data

The subject product, OOCA® image Smart CXR Image Processing System has been evaluated and verified in accordance with software specifications and applicable performance standards to ensure performance.

The separation of the model training dataset and performance assessment dataset

We split dataset into two parts: a model training dataset and a performance assessment dataset. The training dataset is used to train the model, and divided into three sets: the training set, the validation set, and the test set. The performance assessment dataset is used to valid the model's performance. By using a separate performance assessment dataset, we can get a better idea of how well the model will perform in the real world.

All data was carefully managed to prevent overlap and ensure that each dataset was completely independent by using accession numbers and patient IDs. The model training dataset was collected from two hospitals, and additional data from the US National Institutes of Health (NIH) was added to the test set to improve its US patient population representativeness during training. For performance assessment, the US patient population data form MIMIC dataset and a medical institution independent of model training dataset were used. This helped us get a better idea of how well the model would perform in the real world. To avoid any potential biases,

{11}------------------------------------------------

the data for the model training dataset and the performance assessment dataset were carefully chosen and separated.

Performance assessment

The performance of the subject device, QOCA® image Smart CXR Image Processing System, has been validated in two separate pivotal studies. The two studies were performed with the data from the MIMIC dataset and a Taiwanese hospital respectively. The performance of the subject device across the performance assessment dataset achieves an area under the curve (AUC) of 97.8% (95% CI: [97.0%. 98.5%]: in addition, the sensitivity and specificity achieves 92.5% (95% CI: [90.5%, 94.2%]), 94.0% (95% CI: [93.9%, 94.6%]) respectively, without subgroup breakdown. This performance is substantially equivalent to the predicate device (K190362); AUC of 98.3% (95% CI: [97.40%, 99.02%]), the sensitivity and specificity is 93.15% (95% CI: [87.76%, 96.67%]) and 92.99% (95% CI: [90.19%, 95.19%]), respectively.

First, the MIMIC dataset was used to demonstrate the generalizability of the device to the demographics of the US population. The dataset consisted of 3,105 radiographs with 336 positive and 2,769 negative pneumothorax cases. The ethnicities included Asian, Black/African American, Hispanic or Latino, and White. The dataset was truthed by three radiologists. The performance of the subject device to the MIMIC dataset is AUC of 97.7% (95% CI: [96.5%, 98.8%]), the sensitivity and specificity is 93.7% (95% CI: [90.6%, 96.0%]) and 93.3% (95% CI: [92.3%, 94.2%]), respectively.

Characteristics	Subset	Quantity
Age	$22 \le age < 65$	2,449
Age	$65 \le age$	656
Gender	Male	1,516
Gender	Female	1,589
Radiographic positioning	PA view	2,272
Radiographic positioning	AP erect view	24

The characteristics of the MIMIC dataset summarizes in below table:

{12}------------------------------------------------

Characteristics	Subset	Quantity
	Supine view	809
	Asian	200
	Black/African American	402
Race and ethnicity	Hispanic or Latino	598
	White	1,905

Second, the additional Taiwanese dataset was used to demonstrate the generalizability to different imaging equipment. The dataset consisted of 2,947 radiographs with 472 positive and 2,475 negative pneumothorax cases. The dataset was truthed by three radiologists. The performance of the subject device to the Taiwanese dataset is AUC of 97.4% (95% CI: [96.9%, 98.7%]), the sensitivity and specificity is 91.7% (95% CI: [88.8%, 94.0%]) and 94.9% (95% CI: [93.9%, 95.7%]), respectively.

Characteristics	Subset	Quantity
Age	$22 \le age < 65$	2,697
Age	$65 \le age$	250
Gender	Male	1,262
Gender	Female	1,685
Radiographic positioning	PA view	501
Radiographic positioning	AP erect view	1,431
Radiographic positioning	Supine view	1,015
Race and ethnicity	Taiwan population	2,947
Imaging equipment	MRAD-A50S	287
Imaging equipment	MRAD-A80S	185

The characteristics of the Taiwanese dataset summarizes in below table:

Besides, we assessed the performance time of the subject device that reflects the time it takes for the device to analyze the study and send a notification to the worklist. The average performance time of the subject device was 4.94 seconds, and that is substantially equivalent to the predicate (22.1 seconds).

{13}------------------------------------------------

5.10 Conclusion

The subject device has a similar intended use to the predicate device, and the slight difference does not affect the substantial equivalence. In addition, there are no differences in technological characteristics that affect the safety and effectiveness of the subject device relative to the predicate. Moreover, the performance testing results are similar to the predicate device. Therefore, the subject device, QOCA® image Smart CXR Image Processing System, is substantially equivalent to the predicate device.

Regulation Number and Section

§ 892.2080 Radiological computer aided triage and notification software.

(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.